001/* 002 * BioJava development code 003 * 004 * This code may be freely distributed and modified under the 005 * terms of the GNU Lesser General Public Licence. This should 006 * be distributed with the code. If you do not have a copy, 007 * see: 008 * 009 * http://www.gnu.org/copyleft/lesser.html 010 * 011 * Copyright for this code is held jointly by the individual 012 * authors. These should be listed in @author doc comments. 013 * 014 * For more information on the BioJava project and its aims, 015 * or to join the biojava-l mailing list, visit the home page 016 * at: 017 * 018 * http://www.biojava.org/ 019 * 020 * Created on 01-21-2010 021 */ 022package org.biojava.nbio.aaproperties.xml; 023 024import org.biojava.nbio.core.sequence.compound.AminoAcidCompound; 025import org.biojava.nbio.core.sequence.template.CompoundSet; 026import org.biojava.nbio.core.sequence.template.Sequence; 027 028import java.util.*; 029 030/** 031 * Set of proteinogenic amino acids. Molecular weights are recorded in daltons (Da) as residues of a chain; monomers 032 * outside of a chain would likely have an additional mass of 18.01524 Da contributed by an associated water molecule. 033 * 034 * Currently we have different symbols to handle inserts so not as clean as it should be 035 * 036 * @author Richard Holland 037 * @author Scooter Willis 038 * @author Mark Chapman 039 */ 040public class CaseFreeAminoAcidCompoundSet implements CompoundSet<AminoAcidCompound> { 041 042 private final Map<String, AminoAcidCompound> aminoAcidCompoundCache = new HashMap<String, AminoAcidCompound>(); 043 private final Map<AminoAcidCompound, Set<AminoAcidCompound>> equivalentsCache = 044 new HashMap<AminoAcidCompound, Set<AminoAcidCompound>>(); 045 046 public CaseFreeAminoAcidCompoundSet() { 047 aminoAcidCompoundCache.put("A", new AminoAcidCompound(null, "A", "Ala", "Alanine", 71.0788f)); 048 aminoAcidCompoundCache.put("R", new AminoAcidCompound(null, "R", "Arg", "Arginine", 156.1875f)); 049 aminoAcidCompoundCache.put("N", new AminoAcidCompound(null, "N", "Asn", "Asparagine", 114.1039f)); 050 aminoAcidCompoundCache.put("D", new AminoAcidCompound(null, "D", "Asp", "Aspartic acid", 115.0886f)); 051 aminoAcidCompoundCache.put("C", new AminoAcidCompound(null, "C", "Cys", "Cysteine", 103.1388f)); 052 aminoAcidCompoundCache.put("E", new AminoAcidCompound(null, "E", "Glu", "Glutamic acid", 129.1155f)); 053 aminoAcidCompoundCache.put("Q", new AminoAcidCompound(null, "Q", "Gln", "Glutamine", 128.1307f)); 054 aminoAcidCompoundCache.put("G", new AminoAcidCompound(null, "G", "Gly", "Glycine", 57.0519f)); 055 aminoAcidCompoundCache.put("H", new AminoAcidCompound(null, "H", "His", "Histidine", 137.1411f)); 056 aminoAcidCompoundCache.put("I", new AminoAcidCompound(null, "I", "Ile", "Isoleucine", 113.1594f)); 057 aminoAcidCompoundCache.put("L", new AminoAcidCompound(null, "L", "Leu", "Leucine", 113.1594f)); 058 aminoAcidCompoundCache.put("K", new AminoAcidCompound(null, "K", "Lys", "Lysine", 128.1741f)); 059 aminoAcidCompoundCache.put("M", new AminoAcidCompound(null, "M", "Met", "Methionine", 131.1986f)); 060 aminoAcidCompoundCache.put("F", new AminoAcidCompound(null, "F", "Phe", "Phenylalanine", 147.1766f)); 061 aminoAcidCompoundCache.put("P", new AminoAcidCompound(null, "P", "Pro", "Proline", 97.1167f)); 062 aminoAcidCompoundCache.put("S", new AminoAcidCompound(null, "S", "Ser", "Serine", 87.0782f)); 063 aminoAcidCompoundCache.put("T", new AminoAcidCompound(null, "T", "Thr", "Threonine", 101.1051f)); 064 aminoAcidCompoundCache.put("W", new AminoAcidCompound(null, "W", "Trp", "Tryptophan", 186.2132f)); 065 aminoAcidCompoundCache.put("Y", new AminoAcidCompound(null, "Y", "Tyr", "Tyrosine", 163.1760f)); 066 aminoAcidCompoundCache.put("V", new AminoAcidCompound(null, "V", "Val", "Valine", 99.1326f)); 067 aminoAcidCompoundCache.put("B", new AminoAcidCompound(null, "B", "Asx", "Asparagine or Aspartic acid", null)); 068 aminoAcidCompoundCache.put("Z", new AminoAcidCompound(null, "Z", "Glx", "Glutamine or Glutamic acid", null)); 069 aminoAcidCompoundCache.put("J", new AminoAcidCompound(null, "J", "Xle", "Leucine or Isoleucine", null)); 070 aminoAcidCompoundCache.put("X", new AminoAcidCompound(null, "X", "Xaa", "Unspecified", null)); 071 aminoAcidCompoundCache.put("-", new AminoAcidCompound(null, "-", "---", "Unspecified", null)); 072 aminoAcidCompoundCache.put(".", new AminoAcidCompound(null, ".", "...", "Unspecified", null)); 073 aminoAcidCompoundCache.put("_", new AminoAcidCompound(null, "_", "___", "Unspecified", null)); 074 aminoAcidCompoundCache.put("*", new AminoAcidCompound(null, "*", "***", "Stop", null)); 075 076 //Selenocysteine - this is encoded by UGA with the presence 077 //of a SECIS element (SElenoCysteine Insertion Sequence) in the mRNA 078 //and is a post-translation modification 079 aminoAcidCompoundCache.put("U", new AminoAcidCompound(null, "U", "Sec", "Selenocysteine", 150.0388f)); 080 081 //Pyrrolysine is encoded by UAG in mRNA (normally Amber stop codon) which is translated to 082 //this amino acid under the presence of pylT which creates an anti-codon CUA & pylS 083 //which then does the actual conversion to Pyl. 084 aminoAcidCompoundCache.put("O", new AminoAcidCompound(null, "O", "Pyl", "Pyrrolysine", 255.3172f)); 085 086 Map<String, AminoAcidCompound> lowerCaseSet = new HashMap<String, AminoAcidCompound>(); 087 for(String s:this.aminoAcidCompoundCache.keySet()){ 088 lowerCaseSet.put(s.toLowerCase(), this.aminoAcidCompoundCache.get(s)); 089 } 090 this.aminoAcidCompoundCache.putAll(lowerCaseSet); 091 } 092 093 @Override 094 public String getStringForCompound(AminoAcidCompound compound) { 095 return compound.toString(); 096 } 097 098 @Override 099 public AminoAcidCompound getCompoundForString(String string) { 100 if (string.length() == 0) { 101 return null; 102 } 103 if (string.length() > this.getMaxSingleCompoundStringLength()) { 104 throw new IllegalArgumentException("String supplied ("+string+") is too long. Max is "+getMaxSingleCompoundStringLength()); 105 } 106 return this.aminoAcidCompoundCache.get(string); 107 } 108 109 @Override 110 public int getMaxSingleCompoundStringLength() { 111 return 1; 112 } 113 114 115 @Override 116 public boolean isCompoundStringLengthEqual() { 117 return true; 118 } 119 120 private final static CaseFreeAminoAcidCompoundSet aminoAcidCompoundSet = new CaseFreeAminoAcidCompoundSet(); 121 122 public static CaseFreeAminoAcidCompoundSet getAminoAcidCompoundSet() { 123 return aminoAcidCompoundSet; 124 } 125 126 @Override 127 public boolean compoundsEquivalent(AminoAcidCompound compoundOne, AminoAcidCompound compoundTwo) { 128 Set<AminoAcidCompound> equivalents = getEquivalentCompounds(compoundOne); 129 return (equivalents != null) && equivalents.contains(compoundTwo); 130 } 131 132 @Override 133 public Set<AminoAcidCompound> getEquivalentCompounds(AminoAcidCompound compound) { 134 if (equivalentsCache.isEmpty()) { 135 // most compounds are equivalent to themselves alone 136 for (AminoAcidCompound c : aminoAcidCompoundCache.values()) { 137 equivalentsCache.put(c, Collections.singleton(c)); 138 } 139 // ambiguous Asparagine or Aspartic acid 140 addAmbiguousEquivalents("N", "D", "B"); 141 // ambiguous Glutamine or Glutamic acid 142 addAmbiguousEquivalents("E", "Q", "Z"); 143 // ambiguous Leucine or Isoleucine 144 addAmbiguousEquivalents("I", "L", "J"); 145 // ambiguous gaps 146 AminoAcidCompound gap1, gap2, gap3; 147 Set<AminoAcidCompound> gaps = new HashSet<AminoAcidCompound>(); 148 gaps.add(gap1 = aminoAcidCompoundCache.get("-")); 149 gaps.add(gap2 = aminoAcidCompoundCache.get(".")); 150 gaps.add(gap3 = aminoAcidCompoundCache.get("_")); 151 equivalentsCache.put(gap1, gaps); 152 equivalentsCache.put(gap2, gaps); 153 equivalentsCache.put(gap3, gaps); 154 // X is never equivalent, even to itself 155 equivalentsCache.put(aminoAcidCompoundCache.get("X"), new HashSet<AminoAcidCompound>()); 156 } 157 return equivalentsCache.get(compound); 158 } 159 160 // helper method to initialize the equivalent sets for 2 amino acid compounds and their ambiguity compound 161 private void addAmbiguousEquivalents(String one, String two, String either) { 162 Set<AminoAcidCompound> equivalents; 163 AminoAcidCompound cOne, cTwo, cEither; 164 165 equivalents = new HashSet<AminoAcidCompound>(); 166 equivalents.add(cOne = aminoAcidCompoundCache.get(one)); 167 equivalents.add(cTwo = aminoAcidCompoundCache.get(two)); 168 equivalents.add(cEither = aminoAcidCompoundCache.get(either)); 169 equivalentsCache.put(cEither, equivalents); 170 171 equivalents = new HashSet<AminoAcidCompound>(); 172 equivalents.add(cOne); 173 equivalents.add(cEither); 174 equivalentsCache.put(cOne, equivalents); 175 176 equivalents = new HashSet<AminoAcidCompound>(); 177 equivalents.add(cTwo); 178 equivalents.add(cEither); 179 equivalentsCache.put(cTwo, equivalents); 180 } 181 182 @Override 183 public boolean hasCompound(AminoAcidCompound compound) { 184 return aminoAcidCompoundCache.containsValue(compound); 185 } 186 187 @Override 188 public List<AminoAcidCompound> getAllCompounds() { 189 return new ArrayList<AminoAcidCompound>(aminoAcidCompoundCache.values()); 190 } 191 192 193 @Override 194 public boolean isComplementable() { 195 return false; 196 } 197 198 @Override 199 public boolean isValidSequence(Sequence<AminoAcidCompound> sequence) { 200 for (AminoAcidCompound c: sequence) { 201 if (!hasCompound(c)) { 202 return false; 203 } 204 } 205 return true; 206 } 207}